A tremendous need exists for intelligent agents that can be created and edited without resorting to intensive knowledge engineering and programming, and which exhibit believable and variable behavior in the training contexts in which they are deployed. This proposal describes a novel method for creating and editing intelligent agents behavior based on using instance-based modeling and statistical learning methods that learn from the example of a person interacting in a virtual environment. These methods, which leverage structured knowledge in a hybrid symbolic-subsymbolic approach, support automatic incorporation of assessment feedback directly from the interface into an agent, allowing a domain expert to interact with an agent in a closed feedback loop through a participation in a virtual environment, instead of through lengthy reprogramming by a knowledge engineering expert.
Benefit: As gaming type simulation becomes more and more widely used for stand-alone and distributed training as well as for entertainment, a methodology and the tools necessary to evaluate the believability of computer generated entities and NPCs will greatly improve the quality of both the training and the entertainment. The methods and tools proposed in this effort will be designed to be platform independent from both synthetic environment and the behavior model points of view. As new or more existing synthetic environments make their enntity behaviors accessible to other software components, the work done in the completion of these concepts will be directly be useful for making those behaviors more believable with little modification to the tools described in this proposal.
Keywords: non-player characters, non-player characters, virtual simulations, Cognitive architectures, Training, Avatars, systhetic agents, Machine Learning
